© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26297
    Prev
    Next
    INDEX
    Explanations

    пÑĢи, ив, Ð ¿ ÑĢивеÑĤ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    -0.11
    åĴĮåľ°åĮº
    -0.10
    é¢Ī
    -0.09
    ally
    -0.09
    ãģªãĤĬ
    -0.09
    寡
    -0.09
    iros
    -0.09
    å¯Ŀ室
    -0.09
    å£ģåŀĴ
    -0.09
    å¯Ŀ
    -0.09
    POSITIVE LOGITS
    зн
    0.12
    親
    0.10
    зван
    0.09
    voor
    0.09
    èĥ½ä½¿
    0.09
    знак
    0.09
    ework
    0.09
    oux
    0.09
    обÑĢаз
    0.08
    awl
    0.08
    Activations Density 0.038%

    No Known Activations